microsoft/skills-for-fabric

A collection of skills and MCP systems to enable users of CLI, VSCode, Claude to operate over Microsoft Fabric

What it solves

This project provides a collection of reusable AI assistant instructions (skills) that enable AI coding tools to understand and work with Microsoft Fabric. It bridges the gap between general-purpose AI assistants and the specific APIs, query patterns, and operational best practices required for Fabric workloads.

How it works

The project distributes these instructions as bundles or individual skills that can be installed into AI hosts like GitHub Copilot CLI, Claude Code, Cursor, and Windsurf. These skills provide the AI with the necessary context and guidance to perform tasks such as designing medallion architectures or authoring Power BI reports. Additionally, the project includes MCP (Model Context Protocol) servers to provide the AI with live tool access to data sources and APIs.

Who it’s for

Developers and data engineers working with Microsoft Fabric who use AI-powered coding assistants to accelerate their development and operational workflows.

Highlights

  • Broad Fabric Coverage: Includes skills for SQL data warehouse, Spark, Lakehouse, Eventhouse, KQL, Eventstreams, and Dataflows Gen2.
  • Power BI Integration: Dedicated bundles for authoring semantic models, reports, and PBIP workflows.
  • Multi-Tool Support: Compatible with GitHub Copilot CLI, Claude Code, Cursor, Windsurf, and Gemini CLI.
  • Flexible Installation: Supports bundle-level installation via marketplace or granular, single-skill installation using the Agent Package Manager (APM).
  • Live Data Access: Integrates MCP servers to move beyond static instructions to live API and data source interaction.

Related

  • Project
    firebase/agent-skills

    A collection of packaged instructions and scripts that extend AI coding agents' ability to understand and work with Firebase.

  • Project
    mxyhi/ok-skills

    OK Skills is a library of 31 ready‑to‑use *skill packs* for AI coding agents (Codex, Claude Code, Cursor, etc.). Each skill lives in its own directory with a `SKILL.md` that tells the agent how to run the underlying script (e.g., browser automation, docs lookup, planning, design). Install by cloning into `~/.agents/skills` (or the Autohand equivalent), copy the `CLAUDE_AGENTS.md` sections into your agent’s config, and then ask the agent to “Use <skill‑name> …”. The repo provides categories such as Research, Planning, Automation, Frontend, and Utilities, and serves developers who want portable, repeatable AI‑agent capabilities instead of ad‑hoc prompts.

  • Project
    davidondrej/skills

    A curated set of prompt‑based skill definitions for AI coding, research, and ops agents, organized by workflow type and ready to be loaded into Cloudroom or similar agent runtimes.

  • Project
    data-goblin/power-bi-agentic-development

    A marketplace of plugins, skills, and hooks that teaches AI agents like Claude Code and GitHub Copilot how to develop and optimize Power BI and Microsoft Fabric projects.

  • Project
    databricks-solutions/ai-dev-kit

    A toolkit that integrates Databricks expertise and tools into AI-powered code editors, allowing developers to build Databricks pipelines, jobs, and apps using their preferred AI assistants.